A Physics-Informed Neural Network Approach for Fault Diagnosis and Protection in Multi-Source Microgrids
محورهای موضوعی : مهندسی هوشمند برق
Morteza Ghorbani
1
,
Farzad Razavi
2
,
Ahmad Fakharian
3
1 - Department of Electrical Engineering, Qa.C., Islamic Azad University, Qazvin, Iran
2 - Department of Electrical Engineering, Qa.C., Islamic Azad University
3 - Department of Electrical Engineering, Qa.C., Islamic Azad University, Qazvin, Iran
کلید واژه: Power system protection, AC microgrid, fault detection, fault classification, PNN.,
چکیده مقاله :
This paper presented a novel framework based on Physically Informed Neural Networks (PINN) for the protection and monitoring of three-phase microgrids. In order to generate data, a microgrid including distributed generation resources was modeled in the Simulink/Matlab environment and voltage and current data were extracted. Then, the obtained data was transferred to the Google Colab environment, and the proposed algorithm was implemented in the Python platform. The distinctive feature of this approach compared to conventional intelligent methods is the combination of physical laws of the power system with simulated data, which allows for deeper learning of network dynamics and more accurate identification of fault states. The evaluation results show that the proposed model is capable of detecting single-phase, two-phase and three-phase faults even in noisy conditions with an overall accuracy higher than 97%. Furthermore, comparison with conventional machine learning algorithms such as SVM, KNN, DT, RF and ANN showed that the proposed method performs better in terms of stability, accuracy and noise immunity. Therefore, the developed framework can be used as an efficient tool to enhance the stability, reliability and protection of modern microgrids.
This paper presented a novel framework based on Physically Informed Neural Networks (PINN) for the protection and monitoring of three-phase microgrids. In order to generate data, a microgrid including distributed generation resources was modeled in the Simulink/Matlab environment and voltage and current data were extracted. Then, the obtained data was transferred to the Google Colab environment, and the proposed algorithm was implemented in the Python platform. The distinctive feature of this approach compared to conventional intelligent methods is the combination of physical laws of the power system with simulated data, which allows for deeper learning of network dynamics and more accurate identification of fault states. The evaluation results show that the proposed model is capable of detecting single-phase, two-phase and three-phase faults even in noisy conditions with an overall accuracy higher than 97%. Furthermore, comparison with conventional machine learning algorithms such as SVM, KNN, DT, RF and ANN showed that the proposed method performs better in terms of stability, accuracy and noise immunity. Therefore, the developed framework can be used as an efficient tool to enhance the stability, reliability and protection of modern microgrids.
[1] S. A. Hosseini, B. Taheri, S. H. H. Sadeghi, and A. Nasiri, "A deep learning model for fault detection in distribution networks with high penetration of electric vehicle chargers," e-Prime-Advances in Electrical Engineering, Electronics and Energy, vol. 10, p. 100845, 2024.
[2] Y. Li, B. Feng, B. Wang, and S. Sun, "Joint planning of distributed generations and energy storage in active distribution networks: A Bi-Level programming approach," Energy, vol. 245, p. 123226, 2022.
[3] B. Taheri, S. A. Hosseini, and H. Hashemi-Dezaki, "Enhanced fault detection and classification in ac microgrids through a combination of data processing techniques and deep neural networks," Sustainability, vol. 17, no. 4, p. 1514, 2025.
[4] R. Pradhan and P. Jena, "An innovative fault direction estimation technique for AC microgrid," Electric Power Systems Research, vol. 215, p. 108997, 2023.
[5] S. F. Zarei and S. Khankalantary, "Protection of active distribution networks with conventional and inverter-based distributed generators," International Journal of Electrical Power & Energy Systems, vol. 129, p. 106746, 2021.
[6] H. Jahanbani, F. Razavi, and H. Nafisi, "Presenting an innovative single-setting adaptive protection method for AC microgrid with wind turbine," Electrical Engineering, pp. 1-16, 2024.
[7] M. Ghotbi-Maleki, R. M. Chabanloo, H. H. Zeineldin, and S. M. H. Miangafsheh, "Design of setting group-based overcurrent protection scheme for active distribution networks using MILP," IEEE Transactions on Smart Grid, vol. 12, no. 2, pp. 1185-1193, 2020.
[8] S. Shen et al., "An adaptive protection scheme for distribution systems with DGs based on optimized Thevenin equivalent parameters estimation," IEEE Transactions on Power Delivery, vol. 32, no. 1, pp. 411-419, 2015.
[9] J. Ma, X. Wang, Y. Zhang, Q. Yang, and A. Phadke, "A novel adaptive current protection scheme for distribution systems with distributed generation," International Journal of Electrical Power & Energy Systems, vol. 43, no. 1, pp. 1460-1466, 2012.
[10] H. Muda and P. Jena, "Superimposed adaptive sequence current based microgrid protection: A new technique," IEEE Transactions on Power Delivery, vol. 32, no. 2, pp. 757-767, 2016.
[11] B. Taheri and A. Shahhoseini, "Direct current (DC) microgrid control in the presence of electrical vehicle/photovoltaic (EV/PV) systems and hybrid energy storage systems: A Case study of grounding and protection issue," IET Generation, Transmission & Distribution, vol. 17, no. 13, pp. 3084-3099, 2023.
[12] R. Eslami and S. A. Hosseini, "A comprehensive method for fault detection in AC/DC hybrid microgrid," Electric Power Components and Systems, vol. 50, no. 1-2, pp. 38-51, 2022.
[13] H. Huang, Z. Gong, H. Shu, and X. Tian, "Microgrid fault detection method based on sequential overlapping differential transform," in 2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2), 2020: IEEE, pp. 2308-2313.
[14] M. A. Zamani, T. S. Sidhu, and A. Yazdani, "A protection strategy and microprocessor-based relay for low-voltage microgrids," IEEE transactions on Power Delivery, vol. 26, no. 3, pp. 1873-1883, 2011.
[15] B. Taheri, S. A. Hosseini, S. Salehimehr, and F. Razavi, "A novel approach for detection high impedance fault in DC microgrid," in 2019 International Power System Conference (PSC), 2019: IEEE, pp. 287-292.
[16] J. O. C. P. Pinto and M. Moreto, "Protection strategy for fault detection in inverter-dominated low voltage AC microgrid," Electric Power Systems Research, vol. 190, p. 106572, 2021.
[17] F. Zhang and L. Mu, "New protection scheme for internal fault of multi-microgrid," Protection and Control of Modern Power Systems, vol. 4, no. 2, pp. 1-12, 2019.
[18] X. Dong and S. Shi, "Identifying single-phase-to-ground fault feeder in neutral noneffectively grounded distribution system using wavelet transform," IEEE Transactions on Power Delivery, vol. 23, no. 4, pp. 1829-1837, 2008.
[19] D. Mlakić, S. Nikolovski, and H. R. Baghaee, "Cyber–physical machine-learning-based grid-fault detection and location scheme for distance protection of MV distribution lines," International Journal of Electrical Power & Energy Systems, vol. 171, p. 111029, 2025.
[20] Z. Ghanem et al., "Advanced microgrid protection utilizing zero sequence components with Hard-Ware-in-the-Loop testing," IEEE Access, 2025.
[21] A. N. Sheta, A. A. Eladl, B. E. Sedhom, M. I. El-Afifi, P. Sanjeevikumar, and M. Zaki, "Artificial neural network-based enhanced distance protection sensitivity in microgrids," Renewable Energy Focus, vol. 54, p. 100710, 2025.
[22] P. Mahat, Z. Chen, B. Bak-Jensen, and C. L. Bak, "A simple adaptive overcurrent protection of distribution systems with distributed generation," IEEE Transactions on smart grid, vol. 2, no. 3, pp. 428-437, 2011.
[23] W. El-Khattam and T. S. Sidhu, "Resolving the impact of distributed renewable generation on directional overcurrent relay coordination: a case study," IET Renewable power generation, vol. 3, no. 4, pp. 415-425, 2009.
[24] W. K. Najy, H. H. Zeineldin, and W. L. Woon, "Optimal protection coordination for microgrids with grid-connected and islanded capability," IEEE Transactions on industrial electronics, vol. 60, no. 4, pp. 1668-1677, 2012.
[25] S. A. Hosseini, S. H. H. Sadeghi, and A. Nasiri, "Decentralized adaptive protection coordination based on agents social activities for microgrids with topological and operational uncertainties," IEEE Transactions on Industry Applications, vol. 57, no. 1, pp. 702-713, 2020.
[26] Y. Chen, S. Chakraborty, A. Zamzam, and J. Wang, "End-to-end microgrid protection using distributed data-driven methods," Applied Energy, vol. 391, p. 125797, 2025.
[27] P. H. Barra, R. A. Fernandes, and D. V. Coury, "Adaptive hybrid tripping microgrid protection strategy with embedded hardware validation," IEEE Access, 2025.
[28] D. A. Cieslak, M. Moreto, A. E. Lazzaretti, J. R. Junior, F. L. Grando, and T. N. Siemann, "Usage of harmonic synchrophasors for high-impedance fault classification in microgrids," Journal of Control, Automation and Electrical Systems, vol. 35, no. 3, pp. 485-498, 2024.
